Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging open communication and invitations to connect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.18
    ocs
    -0.16
    agen
    -0.15
    ç¯ī
    -0.15
    asio
    -0.14
    pur
    -0.13
     Jog
    -0.13
    ur
    -0.13
    lis
    -0.13
    lav
    -0.13
    POSITIVE LOGITS
    698
    0.19
     anytime
    0.18
     yourself
    0.16
     ìŀIJìľł
    0.15
     freely
    0.15
     ÐĿаÑģ
    0.15
    anking
    0.15
     Shel
    0.14
    .fre
    0.14
    379
    0.14
    Act Density 0.015%

    No Known Activations